Agent frameworks & infrastructure
Multi-agent orchestration
6,185 agents · most starred first
Multi-agent orchestration, page 9 of 62
Agents can work. They cannot declare success. A governed coordination protocol for multi-agent AI work: eight contracts (task, resource, ownership, handoff, verification, evidence, approval, recovery) enforced in code, plus a reproducible conformance benchmark. Apache-2.0 code, CC BY 4.0 specification, zero dependencies, Node 18+.
Interactive multi-agent NCA ecosystem simulation
Build AI-powered predictive maintenance orchestration with Microsoft Foundry, multi-agent workflows, and MCP
AI 智能体专家团队(中文版)— 80+ 个专业 AI 智能体人设,覆盖开发、设计、营销、测试、运维等领域
WSO2 AI Agent Manager is an open control plane designed for enterprises to deploy, manage, and govern AI agents at scale.
Long-running fleet orchestration and memory infrastructure for AI agents. Enables persistent context, shared memory, task execution, and governed coordination across multi-agent systems.
An implementation of "Generative Agents: Interactive Simulacra of Human Behavior"
Multiple instructed-LLMs engage in multi-round "self-questioning" to seek the optimal solution, borrowing from the idea of debate, iteratively refining the current problem-solving process, and finally selecting the optimal solution to give a conclusion.
A Multi-agent reinforcement-learning simulator framework.
SDKs and reference implementations for the Synadia Agent Protocol for NATS
Run fleets of parallel coding agents with governance — Rust control plane for Claude Code & Codex: orchestration, policy, cross-agent review, observability.
Local AI multi-agent orchestration desktop app (Tauri · LangGraph)
An Orchestrate multiple coding agent desktop app
"AI 桌面管家 · 多 Agent 协作编排 · 一句话调动团队完成复杂任务
Task orchestration and engineering delivery for AI agents: definition, assignment, supervision, checks, verification, acceptance and rework. Knowledge/memory provide context. Reusable MCP/CLI capabilities; Claude Code/Codex adapters. Full supervision needs host adaptation and validation. Independently developed; noncommercial.
A self-hosted workspace where people and AI agents work together
Auditable LLM multi-agent town simulation with AgentScope, Mesa, replay, policy experiments, and Streamlit
MIT-licensed Rust framework for multi-agent systems: A2A 1.0, MCP 2026-07-28, three transports
Bellwether 🐏🔔 — Pi package for managing Herdr agents, panes, and runtime sessions from Pi
Mokusei (木犀): a native workspace for coordinating AI agents
Rudder is an orchestration and control platform for agent work, and the operating layer for agent teams.
Aitino is a platform that allows for the creation of crews of AI Agents to help you automate tasks and solve complex problems.
Hivemind — Multi-agent AI team platform
A framework for building nexuses of agents -- where intelligence emerges from interaction, not isolation.
Coding agent orchestration for engineering teams — shipped as a spec plus a working reference implementation.
Build a team of Claude Code / Codex-CLI / Gemini-CLI for your work
Elixir library for lightweight AI agent orchestration inspired by openai/swarm
Traffic light for AI Agents and TypeScript/Node multi-agent orchestrator with shared state, guardrails, and adapters for 32 AI frameworks
A Context Engineering Framework for AI-Assisted Multi Agent Applications Development
Run a team of agents
Multi-Agent AI 工作台 (AgentCore) — 真正的 Agent 团队协作,而非单 Agent 子任务派发
Multi-agent engineering framework: evidence packs, runtime validation, task decomposition, cross-window worker execution, and CI artifact verification for Codex.
AgentNet: Dynamically Graph Structure Selection for LLM-Based Multi-Agent System
This bridge integrates Ollama into any chat interface and lets you build your own multi-agent pipeline, including a built-in memory database.
UVM agents
Codes accompanying the paper "RODE: Learning Roles to Decompose Multi-Agent Tasks (ICLR 2021, https://arxiv.org/abs/2010.01523). RODE is a scalable role-based multi-agent learning method which effectively discovers roles based on joint action space decomposition according to action effects, establishing a new state of the art on the StarCraft multi-agent benchmark.
[NAACL 2025 Demo Track] GenSim: A General Social Simulation Platform with Large Language Model based Agents
本地 AI Agent 协作平台 — slock.ai 的本地开源复刻版,由 Cursor CLI 驱动,无需登录,所有数据 100% 本地存储。
An end to end implementation of Graph Engineering as proposed by Andrew NG and Peter Steinberger
数模Agent(数模 Agent)/ 数学建模 AI 助手:多智能体协作完成题意分析、文献检索、建模、代码执行与论文写作,支持人工审核和断点恢复。Local-first multi-agent workbench for mathematical modeling.
Agent Connect Protocol SDK
Distributed AI agents that work everywhere with no-code UI
Production-ready multi-agent orchestration framework for Claude Code. Features specialized AI agents, automated Git workflows, and comprehensive development automation.
Collaboration infrastructure for AI coding agents | AI 编程代理的协作基础设施
P2P Encrypted Messaging for Agents and People
AI Company로 자동화 조직을 만드세요
AI agent orchestration for open and closed source — a fully customizable fleet of AI agents covering every level of project maintenance, from brainstorming to full autonomy
Pandora is an Agent-Based Modelling framework for large-scale simulations
SpeechAgents: Human-Communication Simulation with Multi-Modal Multi-Agent Systems
Connect agent policies for distributed ML applications
Mexus is a local web console for managing multiple CLI AI Agent instances in parallel.
Multi-agent coordination system for Claude Code with institutional memory
GNAP — Git-Native Agent Protocol. RFC Draft for git-based agent orchestration. Zero servers.
Adaptive Human-Agent Teaming (HAT) & Smart Company (SmC) Infrastructure This repository implements a Human-Model-Free adaptive agent architecture. Instead of relying on rigid, computationally expensive human behavioral models, the system leverages real-time trajectory analysis and the Cross-Entropy
Zero-dep agent workflows with structured approval gates and adversarial review.
Task driven LLM multi agent framework that gives you the building blocks to create anything you wish
Sotopia-π: Interactive Learning of Socially Intelligent Language Agents (ACL 2024)
Python library for building durable and scalable multi-agent orchestrations.
Build autonomous Python agents with native Agent-to-Agent (A2A) communication
Open-source Slack for your AI agent swarm
Fail-closed swarm orchestration with epoch-fenced work and late-completion rejection.
AI orchestration platform
A vast array of examples for the enterprise-grade and production-ready swarms framework.
Multi-agent (path finding) planning framework
Open source code for paper: Multi-Agent Deep Reinforcement Learning Based Multi-Task Partial Computation Offloading in Mobile Edge Computing
A standardized, application-agnostic narrative structure schema designed for reliably transporting authorial intent across multi-agentic narrative systems.
Give your AI team a visible office. Pixel-art RPG workspace for multi-agent collaboration.
Open Dynamic Workflow is a local-first workflow runner for orchestrating external coding-agent CLIs
A Python library for multi-agent planning and pathfinding: CBS, PIBT, LaCAM, LNS, space-time A*, plus decentralized NMPC, velocity obstacles and swarm behaviors
One Hermes conductor. Many coding CLIs. Zero trust in self-reports. Production multi-harness orchestration patterns: worktree lanes, verification gates, recovery playbooks — from 18 kanban boards and every incident that tried to ruin them.
AI-Exchange Protocol (AIXP): A Communication Standard for Artificial Intelligence Agents
Two Heads are Better Than One: Test-time Scaling of Multi-agent Collaborative Reasoning (EMNLP2026)
A multi-agent chatroom for AutoGen agents
Code for Emergent Translation in Multi-Agent Communication
Dynamic decentralized task allocation algorithms for multi-agent systems using auctions and machine learning
Open-source AI agent orchestration platform — self-hosted mission control for autonomous multi-agent systems. Visual DAG workflows, 670+ MCP tools, human-in-the-loop approvals. Works with Claude, GPT-4o, Gemini, Ollama, Codex.
Markdown that steers an LLM is code. Genesis is the architectural layer for designing multi-agent, multi-skill systems -- with named patterns, contracts, and substrate portability, before you write them.
Multi-CLI agent swarm orchestrated by Claude Code: external AI CLIs code in isolated worktrees, Claude verifies and merges
Multi-CLI plugin that orchestrates 49 AI agent personalities (start → plan → build → review → ship) across Claude Code, Codex, Cursor, Copilot, Gemini, Antigravity, Kiro, Windsurf, OpenCode, Kilo, Aider + Kilo Code.
Brigade Stack: run coding agents anywhere and keep one record of the work. Shared tasks, claims, verification receipts, handoffs, and MCP and skills sync for Claude Code, Codex, Cursor, OpenCode, and T3 Code.
A local-first desktop alternative to Grok Bot, OpenBot, T3 Code, Herdr and Orca. Run Claude Code, Codex, Cursor and 13 more coding agents as one team on your own computer: a shared board, agents that check each other’s work, and no account. Free. macOS, Windows, Linux.
Official implementation of MAS-GPT: Training LLMs to Build LLM-based Multi-Agent Systems
[NIPS2025] A decentralized, RAG-enhanced multi-agent framework for LLMs with dynamic task routing and agent evolution.
Research platform for Human-in-the-loop learning (HILL) & Multi-Agent Reinforcement Learning (MARL)
Design Patterns for Multi Agents Frameworks Like Autogen, Langraph, Taskweaver, Crewai,etc
Multi agens orchestration setup for Github Copilot, Cursor, Claude Code, OpenCode, Windsurf, Codex and Antigravity.
Wemux - self-hostable AI agent collaboration platform (Apache-2.0, community edition)
Mind-aware Multi-agent Management Reinforcement Learning
Implementations of MAPPO and IPPO on SMAC, the multi-agent StarCraft environment.
Connect AI agents across any network — zero config, encrypted, skill-based routing
Open-Source Platform for Subagents and Agent Teams. Long-running, collaborative, proactive.
Improved Heuristics for Multi-Agent Path Finding with Conflict-Based Search
An implementation of Emergence of Grounded Compositional Language in Multi-Agent Populations by Igor Mordatch and Pieter Abbeel
[NeurIPS'26] SkillOrchestra: Learning to Route Agents via Skill Transfer
Local-first AI agent workbench: research teams that plan, build and review together, a finance agent, and virtual human companions — in one Electron desktop app.
Rhizome lets Claude Code, Codex, and OpenCode sessions discover each other, follow selected work, and exchange messages through MCP. Use it to coordinate parallel tasks on your laptop or connect your agents with a colleague's agents over a LAN or Tailscale network.
🐊 Multi-Team Intelligent Orchestrator v5.3.1 — DNA-driven multi-agent collaboration with 9 genes, 11-step pipeline, 60+ roles, 6 self-evolution gears. Built for OpenClaw.
DNS-based Agent Identification and Discovery - Reference Implementation for IETF BANDAID
Build an AI team of Hermes agents: SOUL, memory, vault, skills, nightly research, kanban, chief of staff, rituals, and Desktop Bots group chats. Agent-consumable, phase-by-phase guide by Aiona Edge.
Context-central multi-agent framework with PyTorch-like API. Build intelligent agent systems with minimal code.